ai_context - Views

Free text that can provide context to the Omni Agent. Context could include behavioral prompting or example queries and structured Omni results. Refer to the Optimizing models for AI guide for more information on best practices.

Syntax

ai_context: "<context_text>"

Or for multiline context:

ai_context: |
  <multiline_context_text>

Properties

string

Free text that provides context to the Omni Agent. Can include behavioral prompting, instructions for tone, or other guidance to .The following references are supported for this field:

User attributes, referenced with {{omni_attributes.<attribute_name>}}. This allows you to personalize the context for each user.
Model constants, referenced using @{constant_name} syntax. This allows you to maintain reusable instruction blocks such as tone, privacy guidance, and domain context instead of duplicating them.
omni_llm namespace, which allows you to tailor context to specific AI model tiers:
- {{ omni_llm.model }} — Substitutes the active model’s family name, which will be one of: smartest, standard, or fastest
- {{# omni_llm.<family> }}...{{/ omni_llm.<family> }} — Conditional sections for specific model tiers. <family> must be one of smartest, standard, or fastest
- {{^ omni_llm.<family> }}...{{/ omni_llm.<family> }} — Inverse sections, which apply when the specified tier is not used. <family> must be one of smartest, standard, or fastest
See the Examples section for more information.
omni_agent namespace, which allows you to scope context to specific AI agents:
- {{ omni_agent.name }} — Substitutes the active agent’s name, which will be one of: analyze, build, or simple_summarize
- {{# omni_agent.<agent> }}...{{/ omni_agent.<agent> }} — Conditional sections for specific agents. <agent> must be one of analyze, build, or simple_summarize
- {{^ omni_agent.<agent> }}...{{/ omni_agent.<agent> }} — Inverse sections, which apply when the specified agent is not used. <agent> must be one of analyze, build, or simple_summarize
See the Examples section for more information.

Examples

Personalized context using user attributes

ai_context: |
  This view contains data for the {{omni_attributes.region}} region only.

Model-specific query preferences

The following context will apply when the model tier is smartest.

Applies when the model tier is smartest

ai_context: |
  {{# omni_llm.fastest }}
  Prefer queries using pre-aggregated fields when available.

  You are running on {{ omni_llm.model }}.
  {{/ omni_llm.fastest }}

The following context will apply when the model tier is not smartest.

Applies when the model tier is not smartest

  {{^ omni_llm.fastest }}
  You may compute aggregations on-the-fly if needed for accuracy.

  You are running on {{ omni_llm.model }}.
  {{/ omni_llm.fastest }}

Agent-specific context

The following context provides different guidance to different agents based on view-level concerns.

Agent-specific view guidance

ai_context: |
  This view contains pre-aggregated sales metrics.

  {{# omni_agent.analyze }}
  When querying this view, you can use the pre-calculated total_revenue field directly rather than summing line items.
  {{/ omni_agent.analyze }}

  {{# omni_agent.simple_summarize }}
  This view is optimized for dashboard summaries. All measures are pre-aggregated.
  {{/ omni_agent.simple_summarize }}

  {{# omni_agent.build }}
  This view aggregates data at the daily level. The grain is date + product_id.
  {{/ omni_agent.build }}

Using constant references

Reference constants to combine reusable context blocks with view-specific guidance:

View file with constant references

ai_context: |
  @{tone} @{privacy_high}
  This view contains customer transaction data.

The constant references will be substituted with the values defined in the model file.

Behavioral prompting

ai_context: |
  you are the head of finance. you are concerned with the status of customer payments. you often need to project into the future how many invoices are due and for how much. you also need to know if any invoices are late so you can reach out to those customers.

Structured query

ai_context: |
  question: which customers are behind due on payment?
    answer:
    {
    "limit": 1000,
    "sorts": [
      {
        "column_name": "share_rillet_omni_omni__invoices.due_date",
        "sort_descending": true,
        "is_column_sort": false,
        "null_sort": "OMNI_DEFAULT"
      }
    ],
    "table": "share_rillet_omni_omni__invoices",
    "fields": [
      "share_rillet_omni_omni__invoices.customer_id",
      "share_rillet_omni_omni__invoices.customer_name",
      "share_rillet_omni_omni__invoices.invoice_number",
      "share_rillet_omni_omni__invoices.due_date",
      "share_rillet_omni_omni__invoices.total_amount"
    ],
    "pivots": [],
    "dbtMode": false,
    "filters": {
      "share_rillet_omni_omni__invoices.due_date": {
        "is_negative": false,
        "kind": "BEFORE",
        "right_side": "today",
        "type": "date",
        "ui_type": "BEFORE"
      },
      "share_rillet_omni_omni__invoices.status": {
        "type": "string",
        "kind": "EQUALS",
        "values": [
          "unpaid"
        ],
        "is_negative": false,
        "case_insensitive": true
      }
    },
    "modelId": "aeb6f3f4-b0e5-4abb-97eb-eaeb42a16944",
    "version": 5,
    "rewriteSql": true,
    "row_totals": {},
    "fill_fields": [],
    "calculations": [],
    "column_limit": 50,
    "join_via_map": {},
    "column_totals": {},
    "userEditedSQL": "",
    "dimensionIndex": 0,
    "default_group_by": true,
    "join_paths_from_topic_name": "invoices"
  }

Getting started

Manage content

Analyze & build

Visualize & present

Deliver content

Model data

Manage integrations

ai_context - Views

Syntax

Properties

Examples

Personalized context using user attributes

Model-specific query preferences

Agent-specific context

Using constant references

Behavioral prompting

Structured query

​Syntax

​Properties

​Examples

​Personalized context using user attributes

​Model-specific query preferences

​Agent-specific context

​Using constant references

​Behavioral prompting

​Structured query

Syntax

Properties

Examples

Personalized context using user attributes

Model-specific query preferences

Agent-specific context

Using constant references

Behavioral prompting

Structured query